llms.txt checker
llms.txt is a Markdown file that gives language models a short summary of a site and a list of the pages worth reading, proposed at llmstxt.org in September 2024. This checker reads the one at the root of your domain and shows what is in it.
A file is read only by bots that reach your site. The bot access checker shows which do.
Questions
- What is llms.txt?
- A format proposed by Jeremy Howard at llmstxt.org in September 2024: a Markdown file, usually at /llms.txt, that opens with the site’s name as a “# ” heading, may follow it with a short summary in a “> ” quote, and lists the pages worth reading under “## ” headings, one Markdown link per line.
- Do AI assistants read it?
- It is a proposal, not a standard. Google says Google Search ignores it, and 2026 adoption studies show other major AI search crawlers rarely fetch it either. Its readers today are mostly IDE agents and MCP tools that want a short list of a site’s key pages: cheap to publish, but no substitute for good HTML, internal links or structured data.
- What does this checker look at?
- Whether /llms.txt at the root of your domain answers at all, whether it is a text file rather than a web page, whether it opens with the “# ” title the format requires, and what it holds: the summary, the “## ” sections and how many links each one lists. It counts the links; it does not open them.